factual

Post-training proxies for learning speed and R&D capability

Post-training has verifiable proxies: compute or data needed to RL on new environments, how quickly a model learns unseen games or tasks, and benchmarks like Anthropic's CoBench of around 500 real R&D problems, which can become RL environments that let models redo months of frontier progress.

factualpending

Speaker

Dwarkesh Patel

Evidence Quote

“Every benchmark is also an RL environment, and an RL environment like this would allow Anthropic to have its models practice redoing the last three to six months of human progress at the frontier.”

Source

Dwarkesh Patel Podcast - The avalanche that hit math is coming for AI development— Dwarkesh Patel Podcast
Created: 11/17/2026, 6:27:26 AM

Your notes

Loading notes...